© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 19138
    Prev
    Next
    INDEX
    Explanations

    in

    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
     Its
    -0.10
     its
    -0.09
     and
    -0.08
    Its
    -0.08
     some
    -0.08
     States
    -0.08
     Complex
    -0.08
     Some
    -0.07
     bunun
    -0.07
     Factors
    -0.07
    POSITIVE LOGITS
     الهواء
    0.19
     воздух
    0.18
    空气
    0.16
     воздуха
    0.15
     हवा
    0.15
    ’air
    0.14
     воздуш
    0.14
     էն
    0.14
     ауа
    0.14
    ԥхь
    0.13
    Activations Density 0.009%

    No Known Activations