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. 111913
    Prev
    Next
    INDEX
    Explanations

    Enter key (coding)

    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
     with
    -0.09
     manipulation
    -0.07
     manipulated
    -0.07
     судеб
    -0.07
     지역
    -0.07
    大利
    -0.07
    with
    -0.07
     ملکی
    -0.07
     Perr
    -0.07
    arges
    -0.07
    POSITIVE LOGITS
     newline
    0.12
     poems
    0.11
    Submit
    0.10
    Textarea
    0.10
    textarea
    0.10
     Poems
    0.10
    kbd
    0.10
     keyboards
    0.10
    submit
    0.10
     клав
    0.09
    Activations Density 0.002%

    No Known Activations