© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 51139
    Prev
    Next
    INDEX
    Explanations

    analysis

    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
     ------
    -0.10
     ✔
    -0.10
     legalized
    -0.09
     ////
    -0.09
     -----
    -0.09
    verts
    -0.09
    Cols
    -0.08
     LVS
    -0.08
     -------
    -0.08
     %[
    -0.08
    POSITIVE LOGITS
    <|message|>
    0.29
    <|end|>
    0.11
    Think
    0.10
    Thinking
    0.10
    Considering
    0.10
    Before
    0.10
    Proceed
    0.10
    To
    0.10
    Here
    0.10
    Let's
    0.10
    Activations Density 0.064%

    No Known Activations