© 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 EvalsExportsAPI 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. 49502
    Prev
    Next
    INDEX
    Explanations

    V

    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
     comen
    -0.09
     похуд
    -0.09
     lyric
    -0.08
     egl
    -0.08
     ગીત
    -0.08
    okeo
    -0.08
     Liberal
    -0.08
     vp
    -0.08
     boste
    -0.08
     тщ
    -0.08
    POSITIVE LOGITS
    Center
    0.14
    PN
    0.14
    Sphere
    0.13
    pn
    0.12
    Net
    0.12
    IRTUAL
    0.12
    Ms
    0.12
    Server
    0.12
    irtual
    0.12
    ulnerability
    0.11
    Activations Density 0.007%

    No Known Activations