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. 48955
    Prev
    Next
    INDEX
    Explanations

    Bouncing/reflection in code

    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
    ul
    -0.07
    .args
    -0.07
     tortured
    -0.07
    args
    -0.07
     supporters
    -0.07
     advocates
    -0.07
     Riz
    -0.07
     vrst
    -0.07
     votes
    -0.07
     artific
    -0.07
    POSITIVE LOGITS
     bounced
    0.11
     bounce
    0.09
    Bang
    0.09
     bouncing
    0.09
    Bounce
    0.09
     bang
    0.09
     sideways
    0.09
     Bounce
    0.09
     dobl
    0.08
     彭
    0.08
    Activations Density 0.006%

    No Known Activations