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. 9065
    Prev
    Next
    INDEX
    Explanations

    Lengthy descriptions

    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
    Vals
    -0.08
    Values
    -0.08
    antal
    -0.08
     الوا
    -0.07
    embo
    -0.07
    isee
    -0.07
    Algo
    -0.07
    ovia
    -0.07
    acr
    -0.07
    icelo
    -0.07
    POSITIVE LOGITS
    �
    0.09
     telefonu
    0.08
    ’époque
    0.08
     fort
    0.08
     zat
    0.07
    (-(
    0.07
    했던
    0.07
    電話
    0.07
     foam
    0.07
     bolt
    0.07
    Activations Density 0.000%

    No Known Activations