© 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. 19-RESID-POST-AA
    11. 103140
    Prev
    Next
    INDEX
    Explanations

    Making a claim

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     გაი
    -0.11
    врийн
    -0.09
    িৱ
    -0.09
     mbeidh
    -0.09
     өнг
    -0.09
     გაე
    -0.09
    different
    -0.09
     გაიზ
    -0.09
     לפת
    -0.08
     үе
    -0.08
    POSITIVE LOGITS
     주장
    0.20
    认为
    0.19
     assumption
    0.18
     assertion
    0.18
     asserting
    0.18
     दावा
    0.17
    Assertion
    0.17
     assertions
    0.16
     asserts
    0.16
     판단
    0.16
    Activations Density 0.288%

    No Known Activations