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. 12758
    Prev
    Next
    INDEX
    Explanations

    first quadrant

    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
     rehearsal
    -0.09
     בנ
    -0.08
     huren
    -0.07
     Foundation
    -0.07
     бара
    -0.07
     corticost
    -0.07
     групп
    -0.07
     House
    -0.07
    рей
    -0.07
     cocktails
    -0.07
    POSITIVE LOGITS
     quadrant
    0.12
    Coordinates
    0.10
    _coordinates
    0.10
    _corner
    0.10
     координ
    0.09
    Cone
    0.09
    _polygon
    0.08
    coordinates
    0.08
    Coords
    0.08
    Corner
    0.08
    Activations Density 0.014%

    No Known Activations