© 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. 50984
    Prev
    Next
    INDEX
    Explanations

    say arch

    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
    ends
    -0.09
    スペ
    -0.08
    end
    -0.08
     ends
    -0.08
    ènements
    -0.08
    Looks
    -0.08
     থাকে
    -0.08
     Baut
    -0.08
     sorun
    -0.08
    ેન્ડ
    -0.08
    POSITIVE LOGITS
    arch
    0.13
    ARCH
    0.10
     arch
    0.09
    ാർ
    0.09
    arched
    0.08
     archival
    0.08
    ima
    0.08
    Arch
    0.08
    299
    0.08
    обр
    0.08
    Activations Density 0.000%

    No Known Activations