© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 12994
    Prev
    Next
    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ऑ
    -0.08
    SITE
    -0.08
     broad
    -0.08
    ffective
    -0.08
    /community
    -0.08
    updates
    -0.08
    weig
    -0.08
    _site
    -0.07
    游
    -0.07
     laissez
    -0.07
    POSITIVE LOGITS
     disse
    0.09
     Annie
    0.08
     Screw
    0.08
     Admit
    0.08
     cavities
    0.08
     cias
    0.08
     Tesla
    0.08
     Acrobat
    0.08
     Mountain
    0.08
     Cube
    0.08
    Activations Density 0.004%

    No Known Activations