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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 5839
    Prev
    Next
    INDEX
    Explanations

    Math symbols

    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
    \(
    -0.10
    \
    -0.10
    \Form
    -0.10
    \User
    -0.10
    {name
    -0.10
    \Exception
    -0.09
    (this
    -0.09
    ayaran
    -0.09
    \web
    -0.09
    itions
    -0.09
    POSITIVE LOGITS
     frac
    0.10
     |_|
    0.09
    xff
    0.08
     】
    0.08
     coef
    0.08
     '''↵
    0.08
     streng
    0.08
     '''↵↵
    0.08
     MEM
    0.07
     ori
    0.07
    Activations Density 0.052%

    No Known Activations