© 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. 50409
    Prev
    Next
    INDEX
    Explanations

    is

    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
     informational
    -0.08
    izz
    -0.07
    oka
    -0.07
    obo
    -0.07
     din
    -0.07
    ומות
    -0.07
    905
    -0.07
     educational
    -0.07
    othé
    -0.07
    ој
    -0.07
    POSITIVE LOGITS
     prm
    0.09
    ચ્ચ
    0.09
    ке
    0.08
    턴
    0.08
    cling
    0.08
    abet
    0.08
    끌
    0.08
    ાગ
    0.08
    طر
    0.08
    ಿಟ್ಟ
    0.08
    Activations Density 0.000%

    No Known Activations