© 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. 19005
    Prev
    Next
    INDEX
    Explanations

    alleles

    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
     потол
    -0.10
     phone
    -0.08
     Vine
    -0.08
    headers
    -0.08
    seconds
    -0.08
    phone
    -0.08
    _phone
    -0.08
     Phone
    -0.08
     kitchen
    -0.07
    figure
    -0.07
    POSITIVE LOGITS
     allele
    0.30
     alle
    0.22
    Alle
    0.19
     homo
    0.18
     Alle
    0.17
    alle
    0.16
     hap
    0.16
     variant
    0.14
     genotype
    0.14
     variants
    0.14
    Activations Density 0.006%

    No Known Activations