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. 24032
    Prev
    Next
    INDEX
    Explanations

    (

    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
     nurse
    -0.08
    IBOutlet
    -0.08
    OOL
    -0.08
     SCI
    -0.08
    776
    -0.08
     snap
    -0.07
     luk
    -0.07
     grill
    -0.07
     isolamento
    -0.07
     NIH
    -0.07
    POSITIVE LOGITS
     reminiscent
    0.09
    ??
    0.08
     renamed
    0.07
     guerra
    0.07
     translates
    0.07
     planes
    0.07
    Hund
    0.07
     catastroph
    0.07
     messy
    0.07
    �
    0.07
    Activations Density 0.005%

    No Known Activations