© 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. 49363
    Prev
    Next
    INDEX
    Explanations

    competencies

    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
     apartment
    -0.08
     hurry
    -0.08
     suplement
    -0.08
    举办
    -0.08
     Hurry
    -0.08
    胆拖
    -0.08
     dildo
    -0.08
    >manual
    -0.08
    舒服
    -0.08
     apartamento
    -0.08
    POSITIVE LOGITS
     competencies
    0.23
     Kompetenz
    0.21
     competency
    0.20
     competências
    0.20
     Kompet
    0.20
     competencias
    0.20
     Compet
    0.19
    Compet
    0.19
     компет
    0.18
     competence
    0.18
    Activations Density 0.063%

    No Known Activations