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. 24352
    Prev
    Next
    INDEX
    Explanations

    c

    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
    сов
    -0.08
    leiter
    -0.08
     fict
    -0.07
    -0.07
     absurd
    -0.07
     enabled
    -0.07
    classic
    -0.07
     wc
    -0.07
     miraculous
    -0.07
    XYZ
    -0.07
    POSITIVE LOGITS
     réserve
    0.08
     Going
    0.08
     priprav
    0.08
     Seine
    0.08
     Bas
    0.07
     neden
    0.07
     publicidad
    0.07
     babel
    0.07
     بازی
    0.07
    Thunder
    0.07
    Activations Density 0.000%

    No Known Activations