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. 8791
    Prev
    Next
    INDEX
    Explanations

    geometry problems

    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
     bhi
    -0.08
    nn
    -0.08
     also
    -0.08
     امنیت
    -0.08
     subjective
    -0.08
     yom
    -0.07
     rechargeable
    -0.07
     �
    -0.07
    akan
    -0.07
    (',')↵
    -0.07
    POSITIVE LOGITS
    result
    0.09
     Coordin
    0.09
    @Mapper
    0.09
    $result
    0.09
    .result
    0.09
     ratios
    0.09
     résult
    0.09
    .Result
    0.08
    .cent
    0.08
     результ
    0.08
    Activations Density 0.046%

    No Known Activations