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. 112841
    Prev
    Next
    INDEX
    Explanations

    hold

    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
    'action
    -0.09
    ’action
    -0.08
     Aviation
    -0.08
     güne
    -0.08
     Cairo
    -0.07
     '**
    -0.07
    'homme
    -0.07
    'M
    -0.07
    ׳
    -0.07
     aviation
    -0.07
    POSITIVE LOGITS
     withholding
    0.14
     withheld
    0.14
     hostage
    0.11
     gating
    0.11
     locked
    0.10
     restrict
    0.10
     restricting
    0.09
     Locked
    0.09
    restrict
    0.09
     lockdown
    0.09
    Activations Density 0.077%

    No Known Activations