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. 9241
    Prev
    Next
    INDEX
    Explanations

    Reconsideration

    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
    []);↵
    -0.09
     simmer
    -0.08
     prazo
    -0.08
    >>;↵
    -0.08
     plazo
    -0.08
     Pasadena
    -0.08
     треб
    -0.08
    elopen
    -0.08
    !;↵
    -0.08
    ной
    -0.07
    POSITIVE LOGITS
    Mg
    0.07
     aspects
    0.07
    \uff
    0.07
    డం
    0.07
     alternative
    0.07
    Fb
    0.07
     protective
    0.07
     speculative
    0.07
    これは
    0.07
    ucksack
    0.07
    Activations Density 0.061%

    No Known Activations