© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18548
    Prev
    Next
    INDEX
    Explanations

    Cost

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    čno
    -0.09
    andidato
    -0.09
     preparado
    -0.08
     Yet
    -0.08
     prepared
    -0.08
     Applicant
    -0.08
     ಠ
    -0.07
     wee
    -0.07
    posed
    -0.07
     candidato
    -0.07
    POSITIVE LOGITS
    _cost
    0.10
     costs
    0.10
    Kosten
    0.10
     costos
    0.09
     비용
    0.09
     costes
    0.09
     cost
    0.09
    Costs
    0.09
     लागत
    0.09
     kautta
    0.09
    Activations Density 0.001%

    No Known Activations