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. 44203
    Prev
    Next
    INDEX
    Explanations

    than

    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
     निभ
    -0.09
     निर्व
    -0.08
    ொரு
    -0.08
     piste
    -0.08
    िवार
    -0.08
    istant
    -0.08
     grape
    -0.07
    ാള
    -0.07
    !,↵
    -0.07
     pyst
    -0.07
    POSITIVE LOGITS
     ćemo
    0.08
     tym
    0.08
    sorted
    0.08
    .less
    0.07
     made
    0.07
    wel
    0.07
     pró
    0.07
    (sorted
    0.07
     sorted
    0.07
     lik
    0.07
    Activations Density 0.017%

    No Known Activations