© 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. 23-RESID-POST-AA
    11. 5933
    Prev
    Next
    INDEX
    Explanations

    say "og" ending

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sampler
    -0.07
    /add
    -0.07
    _AD
    -0.07
    iali
    -0.07
     keyword
    -0.07
    Simulator
    -0.07
     immersive
    -0.07
    ******/
    -0.07
    まして
    -0.07
     säl
    -0.07
    POSITIVE LOGITS
     звук
    0.10
    rah
    0.08
     Raf
    0.08
     збор
    0.08
    Rah
    0.08
    Ron
    0.08
     Dés
    0.08
    lé
    0.08
     ум
    0.08
     Leah
    0.08
    Activations Density 0.000%

    No Known Activations