© 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. 96875
    Prev
    Next
    INDEX
    Explanations

    say "gr" words

    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
    ග
    -0.09
    ்மை
    -0.08
     GEM
    -0.08
     والاست
    -0.08
    }><
    -0.08
    ギ
    -0.08
    ගම
    -0.07
     steken
    -0.07
     stij
    -0.07
     corresponde
    -0.07
    POSITIVE LOGITS
    pressive
    0.13
    ressant
    0.11
    pression
    0.10
    ression
    0.10
    ressive
    0.10
    ress
    0.08
    ressed
    0.08
    nn
    0.08
    ressing
    0.08
    pressed
    0.08
    Activations Density 0.000%

    No Known Activations