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. 48983
    Prev
    Next
    INDEX
    Explanations

    Code

    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
     THREE
    -0.08
    -0.08
    Ql
    -0.08
    (Camera
    -0.07
    (rotation
    -0.07
    agles
    -0.07
     inversion
    -0.07
    ാള്
    -0.07
    ktober
    -0.07
     Minis
    -0.07
    POSITIVE LOGITS
    ,,,,
    0.08
    <td
    0.08
    ?,?,?,?,
    0.08
     gep
    0.08
    -muted
    0.07
    Anon
    0.07
    _literal
    0.07
    Literal
    0.07
    enseur
    0.07
    [href
    0.07
    Activations Density 0.006%

    No Known Activations