Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11684
    Prev
    Next
    INDEX
    Explanations

    3D models and matrices

    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
    街
    -0.08
    STS
    -0.08
    Street
    -0.08
    uale
    -0.07
     एस
    -0.07
     erectile
    -0.07
    渠道
    -0.07
     impot
    -0.07
     Street
    -0.07
    inas
    -0.07
    POSITIVE LOGITS
     rotations
    0.08
    (shape
    0.08
     inserted
    0.08
    .shape
    0.08
     geplaatst
    0.08
     глоб
    0.08
     ге
    0.08
    _rotation
    0.08
     geometr
    0.08
    .present
    0.08
    Activations Density 0.002%

    No Known Activations