© 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. 18734
    Prev
    Next
    INDEX
    Explanations

    │

    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
     bestimmten
    -0.09
     :,
    -0.09
     *,
    -0.09
     DOES
    -0.09
    :@"
    -0.08
     complejo
    -0.08
     *>(
    -0.08
     @"
    -0.08
     ',',
    -0.08
    ignty
    -0.08
    POSITIVE LOGITS
    ──
    0.14
    0.10
    0.10
    ----
    0.10
    ────
    0.10
     fair
    0.10
    	private
    0.10
    =======↵
    0.09
    	r
    0.09
    	public
    0.09
    Activations Density 0.002%

    No Known Activations