© 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. 51785
    Prev
    Next
    INDEX
    Explanations

    That

    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
     그것
    -0.10
     It'll
    -0.09
     môže
    -0.09
     이러한
    -0.09
     it'll
    -0.09
     It
    -0.09
     costuma
    -0.09
     it
    -0.09
     ایسا
    -0.09
     ĝi
    -0.09
    POSITIVE LOGITS
     means
    0.20
    means
    0.16
     значит
    0.16
     mean
    0.15
    ’s
    0.15
     gives
    0.15
     Means
    0.14
     suggests
    0.14
     signifie
    0.14
     significa
    0.14
    Activations Density 0.079%

    No Known Activations