© 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. 102841
    Prev
    Next
    INDEX
    Explanations

    achieve

    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
    better
    -0.10
     advantageous
    -0.09
     millor
    -0.09
     clearer
    -0.09
     Better
    -0.09
     aiding
    -0.09
     betere
    -0.09
    -aware
    -0.09
    Better
    -0.09
     besser
    -0.08
    POSITIVE LOGITS
     achieve
    0.13
     lograr
    0.12
     добиться
    0.12
    稳赢
    0.12
     해결
    0.12
     accomplish
    0.11
    'obtenir
    0.10
     logra
    0.10
    达到
    0.10
     решить
    0.10
    Activations Density 0.005%

    No Known Activations