© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18770
    Prev
    Next
    INDEX
    Explanations

    misinformation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     limites
    -0.10
     limits
    -0.09
     initials
    -0.09
    kbd
    -0.09
     letten
    -0.09
     specifics
    -0.08
     details
    -0.08
     limitations
    -0.08
     respondeu
    -0.08
     포함
    -0.08
    POSITIVE LOGITS
     misinformation
    0.23
     misleading
    0.18
     propaganda
    0.17
     प्रचार
    0.16
     misguided
    0.16
     falsely
    0.16
    宣传
    0.16
     contradict
    0.15
     deceptive
    0.15
    推广
    0.15
    Activations Density 0.028%

    No Known Activations