© 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. 19-RESID-POST-AA
    11. 19077
    Prev
    Next
    INDEX
    Explanations

    say "+,-,与"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     combinatie
    -0.11
     kombiniert
    -0.10
     gecombineerd
    -0.09
    Combination
    -0.09
     combination
    -0.09
     combinaison
    -0.09
     kombin
    -0.09
     البته
    -0.09
    .choose
    -0.09
     combinação
    -0.09
    POSITIVE LOGITS
    ，与
    0.14
    与
    0.14
    –
    0.14
     与
    0.13
    與
    0.13
    กับ
    0.13
    -亚洲
    0.13
     -
    0.12
    -The
    0.12
    -日本
    0.11
    Activations Density 0.009%

    No Known Activations