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. 67877
    Prev
    Next
    INDEX
    Explanations

    That's

    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
     magkaroon
    -0.08
     والتي
    -0.08
     CHE
    -0.08
     صن
    -0.08
     επίπε
    -0.08
     esimerkiksi
    -0.08
     mell
    -0.08
     ਉਸ
    -0.08
     específicamente
    -0.08
     मामलों
    -0.07
    POSITIVE LOGITS
     elabor
    0.09
     hopefully
    0.08
     pretty
    0.08
     what
    0.08
    els
    0.08
    렇게
    0.08
     thoroughly
    0.08
     logically
    0.08
    haust
    0.08
    ----------------------------------------------------------------
    0.08
    Activations Density 0.028%

    No Known Activations