© 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. 44781
    Prev
    Next
    INDEX
    Explanations

    defining commands

    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
    יוו
    -0.09
     рекоменда
    -0.09
     壹
    -0.08
     cibl
    -0.08
     טייל
    -0.08
     sidd
    -0.08
    。不
    -0.08
    。在
    -0.08
    'av
    -0.08
     arisen
    -0.08
    POSITIVE LOGITS
    lef
    0.09
     lend
    0.09
    anu
    0.08
    Accent
    0.07
    ouri
    0.07
    rror
    0.07
    lock
    0.07
    lh
    0.07
     wore
    0.07
    abcdefghijkl
    0.07
    Activations Density 0.000%

    No Known Activations