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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102253
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Very
    -0.11
     extremadamente
    -0.11
     zeer
    -0.10
     extrêmement
    -0.10
     Extremely
    -0.10
     extremamente
    -0.09
     exceedingly
    -0.09
    .INVALID
    -0.09
    Very
    -0.09
    보다
    -0.09
    POSITIVE LOGITS
     manageable
    0.23
     doable
    0.18
    manageable
    0.17
     moderate
    0.17
     relatively
    0.16
     small
    0.16
    Manage
    0.15
     tract
    0.15
    small
    0.14
     manage
    0.14
    Activations Density 0.018%

    No Known Activations