© 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. 19-RESID-POST-AA
    11. 18994
    Prev
    Next
    INDEX
    Explanations

    related to value

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    řejmě
    -0.09
     ensuring
    -0.08
    เ�
    -0.08
     quadru
    -0.07
    ，所以
    -0.07
    irmware
    -0.07
    077
    -0.07
    Hg
    -0.07
     ולכן
    -0.07
     quinta
    -0.07
    POSITIVE LOGITS
     값
    0.12
     values
    0.12
     valores
    0.11
    -values
    0.11
    値
    0.11
     indique
    0.11
     valeurs
    0.11
     indicates
    0.10
    值
    0.10
     waarden
    0.10
    Activations Density 0.010%

    No Known Activations