© 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. 23-RESID-POST-AA
    11. 51597
    Prev
    Next
    INDEX
    Explanations

    433

    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
    रो
    -0.09
    .ticket
    -0.08
    akah
    -0.08
    .enemy
    -0.07
    -operative
    -0.07
    op
    -0.07
    .rev
    -0.07
    ارية
    -0.07
    øver
    -0.07
     rainbow
    -0.07
    POSITIVE LOGITS
     escre
    0.08
     criando
    0.07
     schrieb
    0.07
    elib
    0.07
     calculations
    0.07
     写
    0.07
    Fraction
    0.07
     kurs
    0.07
    lessness
    0.07
     schafft
    0.07
    Activations Density 0.002%

    No Known Activations