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. 55045
    Prev
    Next
    INDEX
    Explanations

    format

    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
     heuristic
    -0.08
    ющими
    -0.07
     costo
    -0.07
     hurd
    -0.07
     Net
    -0.07
    skraft
    -0.07
     развити
    -0.07
     Handbook
    -0.07
    เน
    -0.07
     Counting
    -0.07
    POSITIVE LOGITS
    formatted
    0.09
    <?=$
    0.09
     complying
    0.09
    rax
    0.09
    形式
    0.09
    વિધ
    0.08
     formatted
    0.08
     comply
    0.08
     compliant
    0.08
    .JSONObject
    0.08
    Activations Density 0.004%

    No Known Activations