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. 12689
    Prev
    Next
    INDEX
    Explanations

    programming/software development

    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
     causal
    -0.08
     scenic
    -0.08
     Salary
    -0.08
     energetic
    -0.08
     Тем
    -0.08
    ’écoute
    -0.07
     rd
    -0.07
     Decorative
    -0.07
     quantitative
    -0.07
     tận
    -0.07
    POSITIVE LOGITS
    -like
    0.09
    fu
    0.08
    itol
    0.08
    нам
    0.08
    tron
    0.08
    protobuf
    0.08
     fu
    0.08
    prin
    0.08
    lications
    0.07
    bp
    0.07
    Activations Density 0.075%

    No Known Activations