Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130913
    Prev
    Next
    INDEX
    Explanations

    ex

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chief
    -0.08
     Lesser
    -0.08
    င္း
    -0.08
    indered
    -0.08
    INDER
    -0.08
    plier
    -0.08
    preferred
    -0.08
    .PREFERRED
    -0.07
     corto
    -0.07
    REFERRED
    -0.07
    POSITIVE LOGITS
    -ex
    0.21
    	ex
    0.21
    (ex
    0.20
    .ex
    0.20
    .Ex
    0.19
    'ex
    0.19
    ’ex
    0.18
    _EX
    0.18
    _ex
    0.17
    EX
    0.17
    Activations Density 0.044%

    No Known Activations