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. 74989
    Prev
    Next
    INDEX
    Explanations

    prepositions/conjunctions

    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
     tek
    -0.08
     Raspberry
    -0.08
    ras
    -0.08
     spi
    -0.07
     oko
    -0.07
    re
    -0.07
     Ham
    -0.07
     Getter
    -0.07
    .kt
    -0.07
    ra
    -0.07
    POSITIVE LOGITS
     ஆகிய
    0.09
     ultimately
    0.08
     altogether
    0.08
     तथा
    0.08
     พ
    0.08
    ançais
    0.08
    Because
    0.07
     critic
    0.07
     respectively
    0.07
     judging
    0.07
    Activations Density 1.106%

    No Known Activations