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. 48970
    Prev
    Next
    INDEX
    Explanations

    sex

    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
    kriv
    -0.08
    tten
    -0.08
    סט
    -0.08
    UR
    -0.08
     tn
    -0.08
    stip
    -0.07
    Thomas
    -0.07
     Thomas
    -0.07
     cryptoc
    -0.07
     Ö
    -0.07
    POSITIVE LOGITS
    별
    0.08
     dor
    0.08
     분
    0.08
     chromosomes
    0.08
     rivalry
    0.08
    分快
    0.07
    份
    0.07
     Lon
    0.07
    पाल
    0.07
     HMS
    0.07
    Activations Density 0.005%

    No Known Activations