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. 102754
    Prev
    Next
    INDEX
    Explanations

    "--"

    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
    .gov
    -0.09
    aws
    -0.08
     aprob
    -0.08
     päät
    -0.08
     britann
    -0.08
     sev
    -0.07
    .iso
    -0.07
    .must
    -0.07
     Amerikan
    -0.07
    eed
    -0.07
    POSITIVE LOGITS
     Џ
    0.08
    -shell
    0.08
    leur
    0.08
    -à
    0.08
    աստ
    0.08
    Shell
    0.07
     կարող
    0.07
    ույ
    0.07
     LAD
    0.07
     последнее
    0.07
    Activations Density 0.003%

    No Known Activations