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. 15-RESID-POST-AA
    6. 19378
    Prev
    Next
    INDEX
    Explanations

    Keyboard shortcuts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    完善
    -0.09
     walls
    -0.09
     middels
    -0.08
     polis
    -0.08
    =========
    -0.08
    ========
    -0.08
    ipos
    -0.08
    itys
    -0.08
    வி
    -0.08
     muur
    -0.08
    POSITIVE LOGITS
    快捷
    0.13
     Ctrl
    0.12
    shortcut
    0.10
    Ctrl
    0.10
     shortcuts
    0.10
     Shortcut
    0.10
     shortcut
    0.09
    Shortcut
    0.09
     clavier
    0.09
    .keyboard
    0.09
    Activations Density 0.004%

    No Known Activations