Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 112884
    Prev
    Next
    INDEX
    Explanations

    cost

    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
     Shannon
    -0.09
     بم
    -0.08
     Sne
    -0.08
     इंग
    -0.07
    Sne
    -0.07
    plet
    -0.07
    Saf
    -0.07
    ulan
    -0.07
     पिछले
    -0.07
    CCI
    -0.07
    POSITIVE LOGITS
    .hg
    0.09
     burge
    0.09
     HOR
    0.08
     outweigh
    0.08
    時間
    0.08
     genital
    0.08
     bagi
    0.08
    手续
    0.08
    HOR
    0.08
    �
    0.07
    Activations Density 0.013%

    No Known Activations