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. 112194
    Prev
    Next
    INDEX
    Explanations

    geometry

    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
    hdad
    -0.08
    iranja
    -0.08
    154
    -0.08
     Packers
    -0.08
     Toolkit
    -0.07
     Cardinals
    -0.07
    ograma
    -0.07
    erit
    -0.07
    510
    -0.07
    打一
    -0.07
    POSITIVE LOGITS
     clockwise
    0.10
     east
    0.09
    east
    0.08
     SSE
    0.08
     diagonal
    0.08
    рев
    0.08
     north
    0.08
    -east
    0.08
    _vertical
    0.08
    וע
    0.08
    Activations Density 0.033%

    No Known Activations