© 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. 18542
    Prev
    Next
    INDEX
    Explanations

    say "()"

    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
    ony
    -0.08
     rayon
    -0.08
    रा
    -0.08
    ��
    -0.07
    。然而
    -0.07
    。但是
    -0.07
     radius
    -0.07
    zony
    -0.07
    [\
    -0.07
     slå
    -0.07
    POSITIVE LOGITS
    _fail
    0.10
    _FAIL
    0.09
    .fail
    0.09
     терп
    0.09
     سنگ
    0.08
    .Fail
    0.08
     고민
    0.08
    ตำรวจ
    0.08
     УК
    0.08
    FAIL
    0.08
    Activations Density 0.001%

    No Known Activations