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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 50252
    Prev
    Next
    INDEX
    Explanations

    pre

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    breng
    -0.08
     presenteren
    -0.08
     pursuing
    -0.08
    ույց
    -0.08
     представителей
    -0.08
    ástico
    -0.08
     pursue
    -0.08
     initially
    -0.08
    geois
    -0.08
     procure
    -0.08
    POSITIVE LOGITS
    empt
    0.17
    emption
    0.17
    liminary
    0.16
    decess
    0.15
    /post
    0.15
    VIOUS
    0.14
    cludes
    0.14
    condition
    0.13
    umably
    0.13
    conditions
    0.13
    Activations Density 0.132%

    No Known Activations