© 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. 18720
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

    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
    VIDEO
    -0.09
    wrapped
    -0.09
    meida
    -0.08
     είχε
    -0.08
    micro
    -0.08
     micro
    -0.08
    story
    -0.08
     microfiber
    -0.08
    саў
    -0.08
     утеп
    -0.08
    POSITIVE LOGITS
     Å
    0.09
    Å
    0.09
     atoms
    0.08
    _atoms
    0.08
     atomic
    0.08
    Atoms
    0.08
    angstrom
    0.08
     BON
    0.07
     budou
    0.07
    (atom
    0.07
    Activations Density 0.002%

    No Known Activations