© 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. 50736
    Prev
    Next
    INDEX
    Explanations

    letter B

    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
     KK
    -0.08
    �
    -0.08
    Snap
    -0.08
     �
    -0.08
     konpr
    -0.08
     verhind
    -0.08
    큰
    -0.07
     عج
    -0.07
     квартиру
    -0.07
     enseñ
    -0.07
    POSITIVE LOGITS
    acterial
    0.17
    acteria
    0.17
    iores
    0.14
    acter
    0.14
    iology
    0.14
    iom
    0.13
    io
    0.13
    actér
    0.13
    ios
    0.13
    ior
    0.13
    Activations Density 0.026%

    No Known Activations