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. 120164
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    ressed
    -0.07
     client
    -0.07
    нот
    -0.07
    ressant
    -0.07
     pynt
    -0.07
    Tr
    -0.07
    .De
    -0.07
     penile
    -0.07
     trophy
    -0.07
    Shots
    -0.07
    POSITIVE LOGITS
     cellspacing
    0.09
     jä
    0.08
     Amelia
    0.08
    arsch
    0.08
     likewise
    0.08
     hauts
    0.08
     ...)↵
    0.08
    阪
    0.08
     LIV
    0.08
     GLS
    0.08
    Activations Density 0.161%

    No Known Activations