© 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. 23-RESID-POST-AA
    11. 6359
    Prev
    Next
    INDEX
    Explanations

    Foreign language text

    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
     holding
    -0.08
    holding
    -0.08
     �
    -0.08
    ીમ
    -0.08
    UE
    -0.07
     ממש
    -0.07
    -moving
    -0.07
    oding
    -0.07
    מש
    -0.07
    ୋ
    -0.07
    POSITIVE LOGITS
     Pty
    0.09
    ್ಚ
    0.08
    ط
    0.08
     Recl
    0.08
     پرې
    0.08
     Noon
    0.08
     Progn
    0.08
     RATE
    0.08
     суч
    0.08
     vaj
    0.08
    Activations Density 0.001%

    No Known Activations