© 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. 11-RESID-POST-AA
    11. 8108
    Prev
    Next
    INDEX
    Explanations

    calculations

    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
     affirm
    -0.09
    ，应
    -0.08
    强调
    -0.08
     advocating
    -0.08
     �
    -0.08
     condemn
    -0.08
     �
    -0.08
    _queryset
    -0.08
     Qo
    -0.08
     강조
    -0.08
    POSITIVE LOGITS
     tedious
    0.11
     numeric
    0.10
     proceeded
    0.10
     numerator
    0.10
    Simpl
    0.10
     simplify
    0.09
     Numerical
    0.09
     Numer
    0.09
     simpl
    0.09
     Numeric
    0.09
    Activations Density 0.068%

    No Known Activations