© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 102706
    Prev
    Next
    INDEX
    Explanations

    say operator or zero

    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
    ­ma
    -0.09
    ­ment
    -0.09
    ­↵
    -0.09
     Managing
    -0.09
     Modeling
    -0.08
     modeling
    -0.08
    ­ti
    -0.08
     trang
    -0.08
     whakah
    -0.08
     রহমান
    -0.08
    POSITIVE LOGITS
    00
    0.11
    0
    0.11
    *
    0.10
     multiplied
    0.10
    '*
    0.10
    *(
    0.09
    ()*
    0.09
    000
    0.09
     యొక్క
    0.09
    '=
    0.08
    Activations Density 0.028%

    No Known Activations