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. 15-RESID-POST-AA
    6. 19237
    Prev
    Next
    INDEX
    Explanations

    ement

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .recyclerview
    -0.08
    	Error
    -0.08
    icoes
    -0.08
    _RED
    -0.08
    otypes
    -0.08
    Shaders
    -0.08
    ocratic
    -0.07
     slogans
    -0.07
    	error
    -0.07
    ynomials
    -0.07
    POSITIVE LOGITS
     Between
    0.10
     between
    0.10
    ను
    0.10
    Between
    0.09
     zwischen
    0.09
    _between
    0.09
     между
    0.09
     ఉ
    0.09
     ని
    0.09
     između
    0.09
    Activations Density 0.005%

    No Known Activations