© 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. 3-RESID-POST-AA
    11. 12851
    Prev
    Next
    INDEX
    Explanations

    Em dash

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ).'
    -0.08
    VOC
    -0.08
     वाली
    -0.08
    Mexico
    -0.08
    839
    -0.07
     브
    -0.07
     idem
    -0.07
     컬
    -0.07
     길
    -0.07
    Kath
    -0.07
    POSITIVE LOGITS
    ца
    0.08
     generally
    0.08
    яться
    0.07
    antsi
    0.07
    lc
    0.07
    inherits
    0.07
    ണ
    0.07
     Mini
    0.07
    -lfs
    0.07
     trajectories
    0.07
    Activations Density 0.000%

    No Known Activations