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. 9091
    Prev
    Next
    INDEX
    Explanations

    Agreements and terms

    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
     clientele
    -0.09
    Waypoint
    -0.08
    варт
    -0.08
    Biome
    -0.08
     clients
    -0.08
     vulnerable
    -0.08
    Louis
    -0.08
     scarce
    -0.08
    стру
    -0.08
    ([]);↵
    -0.08
    POSITIVE LOGITS
    checkbox
    0.08
     Previous
    0.08
     checkbox
    0.08
     ല
    0.07
     checkpoints
    0.07
    itaria
    0.07
     před
    0.07
     tent
    0.07
    _checkbox
    0.07
     préalable
    0.07
    Activations Density 0.009%

    No Known Activations