© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96710
    Prev
    Next
    INDEX
    Explanations

    Н

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /MS
    -0.09
    no
    -0.09
     MS
    -0.08
    typen
    -0.08
    workspace
    -0.08
     Buhari
    -0.08
    -MS
    -0.08
    manes
    -0.07
    mere
    -0.07
     Michaels
    -0.07
    POSITIVE LOGITS
    алаш
    0.11
    аяв
    0.11
    ама
    0.10
    атом
    0.09
    өм
    0.08
    काश
    0.08
    ावर
    0.08
    умо
    0.08
    ема
    0.08
    क्क
    0.08
    Activations Density 0.000%

    No Known Activations