© 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. 50604
    Prev
    Next
    INDEX
    Explanations

    Words, possibly foreign

    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
     finite
    -0.08
     �
    -0.08
     Fin
    -0.08
    ijdt
    -0.08
    �
    -0.08
    bind
    -0.07
    -0.07
    .bind
    -0.07
    ijdens
    -0.07
     dense
    -0.07
    POSITIVE LOGITS
     শব্দ
    0.11
     vowels
    0.11
     لفظ
    0.11
     كلمة
    0.11
     palavra
    0.10
     શબ્દ
    0.10
     strlen
    0.10
     शब्द
    0.10
     الكلمات
    0.10
    VARCHAR
    0.10
    Activations Density 0.005%
    No Known Activations