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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 43868
    Prev
    Next
    INDEX
    Explanations

    parach

    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
    <?,
    -0.08
     발견
    -0.08
     scherp
    -0.07
     వివర
    -0.07
     varn
    -0.07
     tino
    -0.07
     enei
    -0.07
    	var
    -0.07
     lighting
    -0.07
     prof
    -0.07
    POSITIVE LOGITS
     parach
    0.09
     canopy
    0.09
     clutch
    0.09
     chute
    0.08
    jection
    0.08
     flyers
    0.08
    Slip
    0.08
     Emergency
    0.08
    nuts
    0.08
     feather
    0.08
    Activations Density 0.006%

    No Known Activations