© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 112452
    Prev
    Next
    INDEX
    Explanations

    data models and columns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    disp
    -0.10
    क्स
    -0.08
    plo
    -0.07
     optimal
    -0.07
     ausgew
    -0.07
    _strlen
    -0.07
    ően
    -0.07
     Ilu
    -0.07
    .Transform
    -0.07
    fila
    -0.07
    POSITIVE LOGITS
    (nullable
    0.12
     nullable
    0.11
    @Many
    0.09
     поле
    0.09
    @Column
    0.09
     가지
    0.09
    (blank
    0.09
    @One
    0.09
     주
    0.08
    nullable
    0.08
    Activations Density 0.006%

    No Known Activations