© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48081
    Prev
    Next
    INDEX
    Explanations

    say "number 2"

    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
    The
    -0.16
    That
    -0.16
    Our
    -0.16
    Having
    -0.15
    When
    -0.15
    Throughout
    -0.15
    Several
    -0.15
    Below
    -0.15
    Because
    -0.15
    Often
    -0.15
    POSITIVE LOGITS
     এছ
    0.11
    此外
    0.11
     కానీ
    0.11
    比如
    0.11
    。↵↵↵↵↵
    0.11
     എന്നാൽ
    0.11
    但
    0.10
     özellikle
    0.10
    但是
    0.10
     Zudem
    0.10
    Activations Density 0.032%

    No Known Activations