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. 48804
    Prev
    Next
    INDEX
    Explanations

    upside

    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
     범
    -0.08
     Shade
    -0.08
     Fellowship
    -0.07
     clauses
    -0.07
     ശ
    -0.07
     साथी
    -0.07
    urable
    -0.07
     തൊഴില
    -0.07
    uelle
    -0.07
     चैन
    -0.07
    POSITIVE LOGITS
     reversed
    0.10
    _flip
    0.10
     inverted
    0.09
     flipped
    0.09
     flip
    0.09
     flipping
    0.09
    flip
    0.09
     Flip
    0.09
    Flip
    0.09
    invert
    0.08
    Activations Density 0.001%

    No Known Activations