© 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. 78966
    Prev
    Next
    INDEX
    Explanations

    of

    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
     dans
    -0.08
     ವೈ
    -0.08
     своб
    -0.08
     rythme
    -0.07
     emb
    -0.07
     unfold
    -0.07
     വൈ
    -0.07
     Freiheit
    -0.07
     Кат
    -0.07
     Kat
    -0.07
    POSITIVE LOGITS
    上述
    0.08
    ื่น
    0.08
     �
    0.08
    _dropdown
    0.08
     ikun
    0.08
     يقع
    0.08
    至少
    0.08
     indice
    0.07
    lowest
    0.07
    ahuan
    0.07
    Activations Density 0.009%

    No Known Activations