© 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. 108799
    Prev
    Next
    INDEX
    Explanations

    Laterality

    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
    @Inject
    -0.08
    _Injected
    -0.07
    Diag
    -0.07
    rgba
    -0.07
    _alpha
    -0.07
    .XR
    -0.07
    Douglas
    -0.07
    Cull
    -0.07
    _unused
    -0.07
    Experiment
    -0.07
    POSITIVE LOGITS
     paraan
    0.09
     miasta
    0.09
    东方
    0.09
     बाज
    0.08
     alternating
    0.08
     spaced
    0.08
     شہر
    0.08
    文字
    0.08
     пары
    0.08
     formatting
    0.08
    Activations Density 0.004%

    No Known Activations