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

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 103398
    Prev
    Next
    INDEX
    Explanations

    say vertical lines

    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
     (
    -0.12
    （
    -0.11
    (
    -0.09
     ({
    -0.08
    /
    -0.08
     in
    -0.08
     (=
    -0.08
     בס
    -0.07
     from
    -0.07
    ilium
    -0.07
    POSITIVE LOGITS
     +:+
    0.11
     NEGLIGENCE
    0.09
    जब
    0.09
    ээд
    0.09
    ასა
    0.09
     SPACE
    0.08
     &)
    0.08
    ��
    0.08
     როდესაც
    0.08
     +#+#+#+#+#+
    0.08
    Activations Density 0.002%

    No Known Activations