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. 114132
    Prev
    Next
    INDEX
    Explanations

    problem analysis

    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
     allemaal
    -0.09
     Lighthouse
    -0.07
    .car
    -0.07
     Helf
    -0.07
                                                                   
    -0.07
    .star
    -0.07
    ैत
    -0.07
     duidelijke
    -0.07
     enca
    -0.07
    prio
    -0.07
    POSITIVE LOGITS
    anj
    0.08
    avier
    0.08
    arette
    0.08
    മായ
    0.07
     targeting
    0.07
     reconocimiento
    0.07
    illet
    0.07
    misc
    0.07
     miscellaneous
    0.07
     enrolling
    0.07
    Activations Density 0.330%

    No Known Activations