Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 0
    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_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     licenci
    -0.08
     pequ
    -0.07
     UNS
    -0.07
    BAD
    -0.07
     SAD
    -0.07
     qualific
    -0.07
     pena
    -0.07
     Pd
    -0.07
     BAD
    -0.07
     lice
    -0.07
    POSITIVE LOGITS
    爱的
    0.08
     thrill
    0.08
     thousand
    0.08
    atel
    0.08
    —
    0.08
    —the
    0.08
     przede
    0.07
     Never
    0.07
     unforgettable
    0.07
    orei
    0.07
    Activations Density 0.054%

    No Known Activations