© 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. 12854
    Prev
    Next
    INDEX
    Explanations

    't

    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
     Nag
    -0.09
     embody
    -0.08
     કો�
    -0.08
     alleg
    -0.08
     figs
    -0.08
     Sami
    -0.07
     Chau
    -0.07
    (loss
    -0.07
     kn
    -0.07
    Nag
    -0.07
    POSITIVE LOGITS
     Asp
    0.08
     argu
    0.08
     tert
    0.07
    spect
    0.07
    enticated
    0.07
     Elk
    0.07
    Dl
    0.07
    elly
    0.07
    arez
    0.07
    ari
    0.07
    Activations Density 0.029%

    No Known Activations