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. 60247
    Prev
    Next
    INDEX
    Explanations

    Code and data tables

    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
    редит
    -0.09
     جدا
    -0.09
    нащ
    -0.09
     qora
    -0.08
     disastr
    -0.08
     جلد
    -0.08
    וואָ
    -0.08
    ווא
    -0.08
    పీ
    -0.08
     קצר
    -0.08
    POSITIVE LOGITS
    geb
    0.07
    Boxes
    0.07
     fa
    0.07
    _ARRAY
    0.07
    _OUTPUT
    0.07
     pas
    0.07
    ophobic
    0.07
     interpr
    0.07
    .util
    0.06
    _CHECK
    0.06
    Activations Density 0.001%

    No Known Activations