© 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. 68088
    Prev
    Next
    INDEX
    Explanations

    unsolved mysteries

    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
    @test
    -0.08
     enabling
    -0.07
     maka
    -0.07
    .min
    -0.07
     aqu
    -0.07
    .enable
    -0.07
    ovne
    -0.07
    oun
    -0.07
    ov
    -0.07
    on
    -0.07
    POSITIVE LOGITS
     mysterious
    0.22
     mystery
    0.21
     enigmatic
    0.21
     রহ
    0.19
     mystérie
    0.19
     mysteries
    0.19
     misterio
    0.19
     unexpl
    0.18
     unclear
    0.18
     Mystery
    0.17
    Activations Density 0.106%

    No Known Activations