© 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. 54792
    Prev
    Next
    INDEX
    Explanations

    organizing information

    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
     spas
    -0.10
     carav
    -0.08
    coeff
    -0.08
     dha
    -0.08
     deadly
    -0.08
     plea
    -0.08
    äär
    -0.08
     syd
    -0.08
    _coeff
    -0.08
     bicy
    -0.08
    POSITIVE LOGITS
     sinnvoll
    0.10
     dédiée
    0.10
     dédi
    0.09
     dedicated
    0.09
     dédié
    0.09
    별
    0.08
     Separate
    0.08
    ’usage
    0.08
    Reserve
    0.08
    用于
    0.08
    Activations Density 0.046%

    No Known Activations