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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29733
    Prev
    Next
    INDEX
    Explanations

    upcoming films and games

    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
     täglich
    -0.09
     täg
    -0.08
    memcmp
    -0.08
     gestern
    -0.08
     하루
    -0.08
     feta
    -0.07
     dagelijks
    -0.07
     daarvoor
    -0.07
     odpor
    -0.07
     tirar
    -0.07
    POSITIVE LOGITS
     Studios
    0.08
    iqu
    0.08
     prépare
    0.08
     Muse
    0.08
    ��
    0.07
     undis
    0.07
     unpublished
    0.07
    Muse
    0.07
    Cue
    0.07
    .src
    0.07
    Activations Density 0.080%

    No Known Activations