© 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. 51851
    Prev
    Next
    INDEX
    Explanations

    say "е" words

    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
    irable
    -0.07
    imbursement
    -0.07
    hnen
    -0.07
    afruit
    -0.07
     stochastic
    -0.07
    -0.07
     andro
    -0.07
    īja
    -0.07
    �
    -0.07
    θή
    -0.07
    POSITIVE LOGITS
     Sp
    0.26
     Es
    0.26
     espec
    0.25
    Sp
    0.25
     Spec
    0.24
    Es
    0.24
     spec
    0.23
     స్ప
    0.23
    Spec
    0.23
     સ્પ
    0.22
    Activations Density 0.010%

    No Known Activations