© 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. 18792
    Prev
    Next
    INDEX
    Explanations

    ~

    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
     porno
    -0.10
     bomber
    -0.10
     nightclub
    -0.09
     erotiske
    -0.09
    aturbate
    -0.09
     亚洲av
    -0.09
     порно
    -0.09
    片在线观看
    -0.09
     nógv
    -0.09
     staan
    -0.09
    POSITIVE LOGITS
     economics
    0.08
    _DEF
    0.08
    _TYPES
    0.08
     Ethereum
    0.07
    SIGN
    0.07
    _EN
    0.07
    _BASIC
    0.07
     agriculture
    0.07
    183
    0.07
     temperature
    0.07
    Activations Density 0.010%

    No Known Activations