© 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. 26618
    Prev
    Next
    INDEX
    Explanations

    "noch" translations

    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
     secur
    -0.07
     Impro
    -0.07
     unjust
    -0.07
     Schweizer
    -0.07
     MW
    -0.07
    /style
    -0.07
     disper
    -0.07
     economy
    -0.07
     nwe
    -0.07
    /tr
    -0.07
    POSITIVE LOGITS
    maals
    0.13
     steeds
    0.10
    ಷ್ಟು
    0.10
     vedno
    0.09
    まだ
    0.08
    xa
    0.08
     belum
    0.08
    未
    0.08
    blast
    0.08
     posebej
    0.08
    Activations Density 0.010%

    No Known Activations