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. 30485
    Prev
    Next
    INDEX
    Explanations

    aton

    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
     Czech
    -0.08
    طلب
    -0.08
     debate
    -0.07
     weigh
    -0.07
     Чех
    -0.07
    Doc
    -0.07
     ozn
    -0.07
     antimicrobial
    -0.07
    Cust
    -0.07
     memb
    -0.07
    POSITIVE LOGITS
     threatens
    0.08
     Alic
    0.08
     roses
    0.08
     algae
    0.08
     anao
    0.07
     воскрес
    0.07
     zingen
    0.07
     riffs
    0.07
    viet
    0.07
     संर
    0.07
    Activations Density 0.001%

    No Known Activations