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. 52831
    Prev
    Next
    INDEX
    Explanations

    overload

    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
     Brian
    -0.09
     Making
    -0.08
     making
    -0.08
    Making
    -0.08
    Brian
    -0.08
     bisexual
    -0.07
     ending
    -0.07
    dod
    -0.07
     Kay
    -0.07
    Ifc
    -0.07
    POSITIVE LOGITS
     exceed
    0.11
     превыш
    0.10
     exceeds
    0.10
     طاقت
    0.10
     dépasse
    0.09
    하거나
    0.09
    하면
    0.09
     violate
    0.09
     인간
    0.09
     출력
    0.08
    Activations Density 0.009%

    No Known Activations