© 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. 11-RESID-POST-AA
    11. 68254
    Prev
    Next
    INDEX
    Explanations

    toss

    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
     scal
    -0.08
    ium
    -0.08
    jš
    -0.07
     cust
    -0.07
     æt
    -0.07
     expedition
    -0.07
    MAX
    -0.07
    cub
    -0.07
     kö
    -0.07
     Scott
    -0.07
    POSITIVE LOGITS
     stirred
    0.08
    Categor
    0.08
    -provoking
    0.08
     politic
    0.08
     drafted
    0.07
     fer
    0.07
     Aub
    0.07
     Gloria
    0.07
     Bam
    0.07
     Baz
    0.07
    Activations Density 0.003%

    No Known Activations