© 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. 23-RESID-POST-AA
    11. 51569
    Prev
    Next
    INDEX
    Explanations

    fact

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    academy
    -0.10
    ating
    -0.09
    ATING
    -0.09
     submitting
    -0.08
     위해
    -0.08
     punish
    -0.08
     סט
    -0.08
    bbc
    -0.08
    punten
    -0.08
    UPS
    -0.08
    POSITIVE LOGITS
    ored
    0.20
    oriz
    0.14
    orear
    0.11
    ORIZATION
    0.11
    ormap
    0.11
    ORIZ
    0.10
    riz
    0.10
    ORIZED
    0.09
    oring
    0.09
    orn
    0.08
    Activations Density 0.001%

    No Known Activations