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. 11825
    Prev
    Next
    INDEX
    Explanations

    coordinates

    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
     conceptual
    -0.08
     conceito
    -0.08
    orget
    -0.08
     entidade
    -0.07
    hape
    -0.07
    ilters
    -0.07
    Lin
    -0.07
     Pantry
    -0.07
     Fauc
    -0.07
    (di
    -0.07
    POSITIVE LOGITS
     Longitude
    0.11
     longitude
    0.11
    longitude
    0.10
    Longitude
    0.09
    .longitude
    0.09
    .lng
    0.08
     लोगो
    0.08
    ास्त
    0.08
    ahanol
    0.08
     kms
    0.07
    Activations Density 0.004%

    No Known Activations