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. 612
    Prev
    Next
    INDEX
    Explanations

    College

    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
     Phillies
    -0.09
     brittle
    -0.08
     Reese
    -0.08
     fanc
    -0.08
     holy
    -0.08
     hearth
    -0.08
     أثناء
    -0.08
     النبي
    -0.08
     السيارة
    -0.08
     tangled
    -0.07
    POSITIVE LOGITS
     vocational
    0.10
     langu
    0.08
    .cas
    0.07
     pcm
    0.07
    urse
    0.07
     workforce
    0.07
     sequ
    0.07
     uro
    0.07
    생
    0.07
    essor
    0.07
    Activations Density 0.017%

    No Known Activations