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. 112772
    Prev
    Next
    INDEX
    Explanations

    Into

    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
     Յ
    -0.09
     կոչ
    -0.09
     δρό
    -0.09
    արվում
    -0.09
    արվ
    -0.09
     Ամ
    -0.09
     Rodgers
    -0.09
     משת
    -0.09
     Խ
    -0.08
     υπουργ
    -0.08
    POSITIVE LOGITS
    .imag
    0.08
     verification
    0.08
    Ladies
    0.07
     чай
    0.07
    .resume
    0.07
    .SE
    0.07
     aver
    0.07
    @m
    0.07
    resume
    0.07
     checking
    0.07
    Activations Density 0.000%

    No Known Activations