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. 77377
    Prev
    Next
    INDEX
    Explanations

    images/photos

    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
    FAX
    -0.08
     Bol
    -0.07
     permeability
    -0.07
     Fa
    -0.07
     Stoke
    -0.07
    BAL
    -0.07
    Bol
    -0.07
    Fort
    -0.07
     Neu
    -0.07
     neurological
    -0.07
    POSITIVE LOGITS
     съем
    0.12
     photographer
    0.10
     picker
    0.10
     caméra
    0.10
     câmera
    0.10
    /gallery
    0.10
     사진
    0.10
     Lightroom
    0.09
     selfie
    0.09
     कैम
    0.09
    Activations Density 0.004%

    No Known Activations