© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 24609
    Prev
    Next
    INDEX
    Explanations

    word usage

    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
    -0.08
     có
    -0.07
     Hans
    -0.07
     Mail
    -0.07
     näch
    -0.07
    .train
    -0.07
     serieus
    -0.07
    662
    -0.07
    .wp
    -0.07
     Pedro
    -0.07
    POSITIVE LOGITS
     whatsoever
    0.10
    nor
    0.10
     никаких
    0.09
     rumours
    0.09
     وعدم
    0.09
     rif
    0.09
    yet
    0.08
    -либо
    0.08
     attempts
    0.08
    ,坚持
    0.08
    Activations Density 0.006%

    No Known Activations