© 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. 3-RESID-POST-AA
    11. 1404
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _axis
    -0.08
     axis
    -0.08
     confin
    -0.08
     Diet
    -0.08
    /AP
    -0.08
    axis
    -0.08
     CONF
    -0.07
     GBR
    -0.07
     AE
    -0.07
     hips
    -0.07
    POSITIVE LOGITS
     inscriptions
    0.08
     inscription
    0.08
    Visit
    0.08
    Visitor
    0.08
     Visitors
    0.08
     quotation
    0.07
     Taste
    0.07
     vad
    0.07
     vowels
    0.07
     noble
    0.07
    Activations Density 0.001%

    No Known Activations