© 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. 51718
    Prev
    Next
    INDEX
    Explanations

    _H

    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
    <Question
    -0.10
    <Unity
    -0.09
    <Hash
    -0.09
    <Date
    -0.09
     आज
    -0.09
    <C
    -0.08
    <Post
    -0.08
     Question
    -0.08
    <Audio
    -0.08
     January
    -0.08
    POSITIVE LOGITS
    Hmm
    0.12
    Kim
    0.08
    Nat
    0.08
    He
    0.08
    ista
    0.08
    Ana
    0.07
    kannten
    0.07
    Ket
    0.07
    Ind
    0.07
    ništ
    0.07
    Activations Density 0.001%

    No Known Activations