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. 11618
    Prev
    Next
    INDEX
    Explanations

    строк

    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
    �
    -0.07
     glaze
    -0.07
     empowers
    -0.07
    128
    -0.07
     mim
    -0.07
    రి
    -0.07
    ాత
    -0.07
     ornate
    -0.06
     expedite
    -0.06
     empower
    -0.06
    POSITIVE LOGITS
     LOS
    0.08
    dcc
    0.08
    -able
    0.08
    .au
    0.08
     koe
    0.08
     xu
    0.08
     Quellen
    0.07
     Gab
    0.07
     Lup
    0.07
    0.07
    Activations Density 0.332%

    No Known Activations