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. 9214
    Prev
    Next
    INDEX
    Explanations

    floor

    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
    ugat
    -0.08
     Mih
    -0.08
    criptor
    -0.08
     sequential
    -0.08
     verspre
    -0.07
    _plate
    -0.07
    Maur
    -0.07
    _channel
    -0.07
    Sud
    -0.07
    Channel
    -0.07
    POSITIVE LOGITS
    ത്തിലെ
    0.07
     pine
    0.07
    ത്തിൽ
    0.07
     th
    0.07
     freckles
    0.07
     ő
    0.07
     palm
    0.07
     posl
    0.07
     wavelengths
    0.07
    ത്ത
    0.07
    Activations Density 0.004%

    No Known Activations