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. 43142
    Prev
    Next
    INDEX
    Explanations

    mathematical proofs

    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
    .Ab
    -0.08
    岗位
    -0.08
     beträgt
    -0.08
     docking
    -0.08
     Seating
    -0.07
     cla
    -0.07
     amper
    -0.07
     dock
    -0.07
    干部
    -0.07
     wurde
    -0.07
    POSITIVE LOGITS
     finit
    0.10
    _RANDOM
    0.10
    Sequences
    0.09
     sequences
    0.09
     indefinitely
    0.09
     sieve
    0.09
     randomness
    0.09
     infinitely
    0.09
     байдаг
    0.09
    rand
    0.09
    Activations Density 0.034%

    No Known Activations