Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 77327
    Prev
    Next
    INDEX
    Explanations

    >

    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
    enery
    -0.08
     }↵//
    -0.08
     Nat
    -0.07
     turb
    -0.07
     Ila
    -0.07
    ursor
    -0.07
     Uzbekistan
    -0.07
     barking
    -0.07
     titulaire
    -0.07
     trough
    -0.07
    POSITIVE LOGITS
     Breakdown
    0.08
     dettagli
    0.08
     diagnostics
    0.07
     schematic
    0.07
     scav
    0.07
     detailing
    0.07
    具体
    0.07
    关键词
    0.07
    几点
    0.07
    详细
    0.07
    Activations Density 0.054%

    No Known Activations