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. 74663
    Prev
    Next
    INDEX
    Explanations

    file manipulation and replacement

    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
    団
    -0.09
    еры
    -0.08
     asociación
    -0.08
    язан
    -0.08
    'association
    -0.08
    -0.07
    ਿਤ
    -0.07
     prensa
    -0.07
    阳市
    -0.07
    ecture
    -0.07
    POSITIVE LOGITS
     inplace
    0.14
     overwrite
    0.13
     overwritten
    0.13
    修改
    0.12
     수정
    0.12
     modification
    0.12
     alteration
    0.11
     overw
    0.11
     overhaul
    0.11
     modifications
    0.11
    Activations Density 0.010%

    No Known Activations