© 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. 49151
    Prev
    Next
    INDEX
    Explanations

    H

    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
    Arch
    -0.08
     শনিবার
    -0.08
     शनिवार
    -0.08
    莎
    -0.08
    Mon
    -0.07
     childish
    -0.07
     Wright
    -0.07
     creatures
    -0.07
     Crash
    -0.07
     Mon
    -0.07
    POSITIVE LOGITS
    ubble
    0.21
    ubbles
    0.14
    -alpha
    0.10
    ST
    0.09
    iggs
    0.09
    utsi
    0.09
    aw
    0.09
    oyle
    0.09
    AW
    0.09
    ulse
    0.09
    Activations Density 0.001%

    No Known Activations