© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19-RESID-POST-AA
    11. 102191
    Prev
    Next
    INDEX
    Explanations

    tail

    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
     eran
    -0.09
     uno
    -0.08
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    -0.08
     ahorro
    -0.08
    емые
    -0.08
     aktive
    -0.08
     akty
    -0.08
    ################################################################
    -0.08
    емся
    -0.08
    IMUM
    -0.08
    POSITIVE LOGITS
    ored
    0.19
    oring
    0.17
    orable
    0.15
    ormap
    0.15
    wind
    0.14
    winds
    0.13
    ândia
    0.12
    or
    0.12
    ors
    0.11
    leur
    0.11
    Activations Density 0.011%

    No Known Activations