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. 45373
    Prev
    Next
    INDEX
    Explanations

    generic letters when details missing

    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
     sortable
    -0.08
    uforia
    -0.08
     fascinated
    -0.08
     쉽게
    -0.08
     �
    -0.08
    Sorter
    -0.07
     Breaking
    -0.07
     riff
    -0.07
    ggy
    -0.07
    -toggle
    -0.07
    POSITIVE LOGITS
     hypothetical
    0.11
     fictional
    0.10
     name
    0.10
     fict
    0.10
     hipot
    0.09
     unspecified
    0.09
     nonprofit
    0.09
     concrete
    0.09
    名字
    0.08
     company's
    0.08
    Activations Density 0.034%

    No Known Activations