© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25156
    Prev
    Next
    INDEX
    Explanations

    set theory

    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
     Mario
    -0.08
     Tib
    -0.08
     fiberglass
    -0.07
     Musk
    -0.07
     Approximately
    -0.07
     Mutex
    -0.07
     Topic
    -0.07
     Enough
    -0.07
    欠
    -0.07
     empleados
    -0.07
    POSITIVE LOGITS
    Companies
    0.09
    _vals
    0.09
    Schedulers
    0.08
    Filt
    0.08
    vals
    0.08
    Calend
    0.08
     VALUES
    0.08
    Vals
    0.08
     filt
    0.08
     preserv
    0.08
    Activations Density 0.030%

    No Known Activations