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. 49478
    Prev
    Next
    INDEX
    Explanations

    Then

    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
     depends
    -0.08
     Imperial
    -0.08
     must
    -0.08
     них
    -0.08
     BSD
    -0.07
    Ub
    -0.07
     வேண்டும்
    -0.07
    must
    -0.07
     Porto
    -0.07
    OTHER
    -0.07
    POSITIVE LOGITS
     resentment
    0.08
    ిక్
    0.08
     kite
    0.08
     denial
    0.08
     tým
    0.07
     Andersen
    0.07
    国家
    0.07
     grip
    0.07
     haciendo
    0.07
     sessões
    0.07
    Activations Density 0.069%

    No Known Activations