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. 88095
    Prev
    Next
    INDEX
    Explanations

    call for help

    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
     thú
    -0.08
     usual
    -0.08
     tyl
    -0.08
    _calc
    -0.08
    'éc
    -0.08
     texture
    -0.07
     berl
    -0.07
    Calc
    -0.07
    DV
    -0.07
     expected
    -0.07
    POSITIVE LOGITS
    .broadcast
    0.12
    broadcast
    0.12
    .Broadcast
    0.12
    喊
    0.12
     broadcasts
    0.12
     loudly
    0.11
     desperate
    0.11
     plea
    0.11
    .alert
    0.11
    /request
    0.11
    Activations Density 0.069%

    No Known Activations