© 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. 685
    Prev
    Next
    INDEX
    Explanations

    semicolon

    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
     데이터
    -0.08
    _par
    -0.07
    PROC
    -0.07
    Aer
    -0.07
     iodine
    -0.07
     별
    -0.07
     IS
    -0.07
     Parcel
    -0.07
     PROC
    -0.07
    Ag
    -0.07
    POSITIVE LOGITS
     heartfelt
    0.09
     earthy
    0.09
     noticeable
    0.08
     mundane
    0.08
     sarcast
    0.08
     წყ
    0.08
     respectable
    0.08
     tragic
    0.08
     sadness
    0.08
     normative
    0.08
    Activations Density 0.005%

    No Known Activations