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. 59695
    Prev
    Next
    INDEX
    Explanations

    fireplace

    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
    Ia
    -0.08
    Download
    -0.08
    distributed
    -0.07
     constituent
    -0.07
     distributed
    -0.07
     Bernstein
    -0.07
    download
    -0.07
     download
    -0.07
    Derivative
    -0.07
    Distributed
    -0.07
    POSITIVE LOGITS
    bord
    0.09
     hearth
    0.09
    room
    0.09
    گاه
    0.09
     отоп
    0.09
    ROOM
    0.09
     calef
    0.08
    bedrijf
    0.08
    boards
    0.08
     cottages
    0.08
    Activations Density 0.004%

    No Known Activations