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. 106170
    Prev
    Next
    INDEX
    Explanations

    4

    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
    _coeff
    -0.08
    .Status
    -0.08
     naveg
    -0.07
     resigned
    -0.07
    所在
    -0.07
    .bits
    -0.07
     resign
    -0.07
     acessar
    -0.07
     navegar
    -0.07
    _res
    -0.07
    POSITIVE LOGITS
     smoothie
    0.08
    .soap
    0.08
     külön
    0.08
     halal
    0.08
     succ
    0.08
    😍
    0.08
     extravagant
    0.08
    nera
    0.08
    rys
    0.08
    mate
    0.07
    Activations Density 0.007%

    No Known Activations