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. 44223
    Prev
    Next
    INDEX
    Explanations

    worst

    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
    (Form
    -0.09
     Independ
    -0.08
    ces
    -0.07
     Etc
    -0.07
     NAB
    -0.07
    yla
    -0.07
     Broadcast
    -0.07
    iring
    -0.07
     cds
    -0.07
     �
    -0.07
    POSITIVE LOGITS
     fermentation
    0.09
     kakhulu
    0.09
    _than
    0.08
     ус
    0.08
     rõ
    0.08
    -than
    0.08
     worse
    0.08
    comed
    0.08
     offenders
    0.08
    frei
    0.08
    Activations Density 0.008%

    No Known Activations