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. 78586
    Prev
    Next
    INDEX
    Explanations

    floor

    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
     gewinnt
    -0.08
     diplomats
    -0.08
     spin
    -0.08
     related
    -0.08
     വ്യക്ത
    -0.07
     capire
    -0.07
     gewann
    -0.07
     querying
    -0.07
     oczy
    -0.07
     цар
    -0.07
    POSITIVE LOGITS
    厚
    0.10
    platten
    0.10
     grd
    0.10
     마련
    0.10
    Thickness
    0.09
    /footer
    0.09
     thickness
    0.09
    pads
    0.09
    zmat
    0.08
    mst
    0.08
    Activations Density 0.012%

    No Known Activations