© 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. 51778
    Prev
    Next
    INDEX
    Explanations

    responsive

    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
     unlucky
    -0.07
    @One
    -0.07
    Nie
    -0.07
     circunst
    -0.07
     выраж
    -0.07
     confl
    -0.07
    ेत्र
    -0.07
     μυ
    -0.07
    tingen
    -0.07
     QObject
    -0.07
    POSITIVE LOGITS
     responsive
    0.43
    Responsive
    0.40
     Responsive
    0.39
     responsiveness
    0.39
    responsive
    0.39
    -responsive
    0.33
     Respons
    0.33
     respons
    0.33
     RESPONS
    0.31
    Respons
    0.30
    Activations Density 0.075%

    No Known Activations