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. 112256
    Prev
    Next
    INDEX
    Explanations

    computer

    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
     partic
    -0.08
     pisa
    -0.08
    ambah
    -0.07
     dessa
    -0.07
     pict
    -0.07
     след
    -0.07
    luiting
    -0.07
     salut
    -0.07
     sfr
    -0.07
     shirk
    -0.07
    POSITIVE LOGITS
    BB
    0.08
    phonique
    0.08
    之一
    0.08
    /helper
    0.08
    ®,
    0.08
    /domain
    0.08
     Gregory
    0.07
    ®
    0.07
     바로
    0.07
    ™,
    0.07
    Activations Density 0.251%

    No Known Activations