© 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. 2608
    Prev
    Next
    INDEX
    Explanations

    SUR

    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
    wear
    -0.07
    mess
    -0.07
     wrap
    -0.07
     fabul
    -0.07
    县
    -0.07
    othing
    -0.07
     arn
    -0.07
     don
    -0.07
    orthy
    -0.07
    science
    -0.07
    POSITIVE LOGITS
     rupa
    0.08
    ілік
    0.08
    حدة
    0.08
     veröffentlicht
    0.08
     इंस
    0.08
    Ifc
    0.07
     MODULE
    0.07
    над
    0.07
    илә
    0.07
     duh
    0.07
    Activations Density 0.000%

    No Known Activations