© 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 EvalsExportsAPI 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. 50269
    Prev
    Next
    INDEX
    Explanations

    anest

    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
    otan
    -0.09
    un
    -0.08
    ak
    -0.08
    Hor
    -0.08
    okk
    -0.08
    kal
    -0.08
    ad
    -0.08
    KA
    -0.07
     walnuts
    -0.07
    orr
    -0.07
    POSITIVE LOGITS
    hetics
    0.11
    hetic
    0.10
    സി
    0.10
    hes
    0.09
    hesia
    0.09
    ępu
    0.09
    ąpi
    0.08
     respiratory
    0.08
    媳
    0.08
    ези
    0.08
    Activations Density 0.002%

    No Known Activations