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. 74701
    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
     voie
    -0.08
    씬
    -0.08
    .UU
    -0.08
    եցնել
    -0.08
    устя
    -0.08
    ாமல்
    -0.08
    ttää
    -0.08
     testified
    -0.08
    чив
    -0.08
     buurt
    -0.08
    POSITIVE LOGITS
    ひ
    0.09
     miteinander
    0.09
     ary
    0.08
     prej
    0.08
     daxil
    0.08
    /book
    0.07
     abra
    0.07
    Fat
    0.07
     Drag
    0.07
    >Error
    0.07
    Activations Density 0.028%

    No Known Activations