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. 58321
    Prev
    Next
    INDEX
    Explanations

    Random snippets of texts

    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
    arque
    -0.08
     evaluates
    -0.08
     arche
    -0.08
     is
    -0.07
     fire
    -0.07
     Pr
    -0.07
    -master
    -0.07
     Arche
    -0.07
     व्यवस्थ
    -0.07
    _fire
    -0.07
    POSITIVE LOGITS
    _TOO
    0.08
    송
    0.08
    .variables
    0.08
     bloginfo
    0.08
    _CONTENT
    0.08
    ойчив
    0.08
     roma
    0.08
    _SO
    0.08
    ーナ
    0.07
     ambient
    0.07
    Activations Density 0.000%

    No Known Activations