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. 55832
    Prev
    Next
    INDEX
    Explanations

    Propriet

    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
     Kräfte
    -0.09
     LSU
    -0.09
     zunächst
    -0.08
     dez
    -0.07
     nóg
    -0.07
     airborne
    -0.07
     Outubro
    -0.07
     Aloe
    -0.07
     അദ്ദേഹം
    -0.07
    substring
    -0.07
    POSITIVE LOGITS
    itis
    0.08
    coffee
    0.08
    Coffee
    0.08
     prácticamente
    0.08
    ura
    0.07
    Shipment
    0.07
    arg
    0.07
     risky
    0.07
     headache
    0.07
    Stars
    0.07
    Activations Density 0.002%

    No Known Activations