© 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. 51209
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    acus
    -0.08
    ileo
    -0.08
    jax
    -0.08
     î
    -0.08
     assort
    -0.07
     Asia
    -0.07
    ainteres
    -0.07
    jeg
    -0.07
     जाना
    -0.07
    लेक
    -0.07
    POSITIVE LOGITS
    ист
    0.14
    евид
    0.13
    ищ
    0.12
    истой
    0.10
    istit
    0.10
    еред
    0.10
    иста
    0.10
    ys
    0.10
    istic
    0.10
    ista
    0.09
    Activations Density 0.001%

    No Known Activations