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. 49848
    Prev
    Next
    INDEX
    Explanations

    mathematics

    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
    Typography
    -0.07
    ğer
    -0.07
    inition
    -0.07
     subscription
    -0.07
    roep
    -0.07
    (wait
    -0.07
    પ્ર
    -0.07
     Geological
    -0.07
    <Mesh
    -0.07
     extinct
    -0.07
    POSITIVE LOGITS
     SINGLE
    0.09
    ulas
    0.08
     Revenge
    0.08
     dawo
    0.08
     бит
    0.08
     EPA
    0.08
     Wellness
    0.08
     Dill
    0.08
     ерек
    0.08
     ESTE
    0.07
    Activations Density 0.018%

    No Known Activations