© 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. 51011
    Prev
    Next
    INDEX
    Explanations

    Russian 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
    čkog
    -0.10
    ческой
    -0.10
    ческого
    -0.10
    sk
    -0.09
    ಕೀಯ
    -0.09
    ської
    -0.09
    ικής
    -0.08
    čkih
    -0.08
    ической
    -0.08
    čku
    -0.08
    POSITIVE LOGITS
    ней
    0.14
    ен
    0.13
    மான
    0.13
    ствие
    0.13
    మైన
    0.12
    ible
    0.12
    ful
    0.12
    ্যম
    0.11
    ствуют
    0.11
    ствует
    0.11
    Activations Density 0.030%

    No Known Activations